I feel like a lot of the elementary curriculum should be updated to the current "101"s of each subject… and everyone should get a “refresher” course, maybe every 10 years, to learn the diff changes.

It would also help to stop treating kids like they’re all stupid; stop teaching oversimplified versions of subjects, only to some years later go “Oh BTW, what we taught you before, that was BS, learn this one instead”.

Some religions to this day decree when a female is “unclean” and should be isolated. The problem are people with that mentality.

The same “yuck” factor lies at the root of not thinking rationally about tampons, abortions, childbirth, lactation, etc. Controlling a population’s approach to inherent bodily functions, has been an effective way of brainwashing for ages. Stuff like vote of celibacy, vote of silence, vote of reclusion, fasting, and similar. Convincing people to sacrifice for a doctrine, gets them invested and pulls them into a sunken cost fallacy.

I’d call it Evil… but that is going onto their territory, so laughing it off with Weird, is probably a better strategy.

Memes have been working better than reality, for thousands of years at this point.

The popularization of democracy, and the multiple orders of magnitude faster and wider communication methods, have only made it more obvious.

I’ve been going to Facebook as of late, following some science, comics, LGBT+, and MLP authors. The off-topic stuff I get, are some news, airplane stuff, dashcam videos, and so on.

I just checked my Twitter feed, it’s full of ponies, furries, space, and some game memes, plus random ads. My alt account is still full of R34.

I get 0 news about where I live, I refuse to follow any politicians or influencers on either platform.

Just opened Chrome, and the first 2 pages of Google suggested links, are all stuff I want to read (mostly science related).

The Algorithm giveth and The Algorithm taketh away. Tame thine Algorithm to thy desire.

The problem is that elected officials are using the unelected tsar’s social media to share official announcements and engage in public debate.

Looks like photo-edited AI? 😜

Put it all into a matrix I would love to see the population distribution across this table.

That would be an interesting thing to see.

However, biology is still learning about human sex. IIRC last year there was a cancer study that put in question a large number of biology studies in general… because many only focused on XY cell lines, to save time, reasoning that “if it has an X, and it has a Y, then all variables are covered”. Well, turns out that XX cells don’t use both chromosomes at the same time; instead, the genes from one of the Xs get inhibited via epigenetics… but not always all of them, or in the same way, and not always on the same X. That means some genes that didn’t activate in XY cells, sometimes would in XX cells, causing different mutations and reactions to cancer medication.

Well, you mentioned they’re photo-taxic.

☝️😯… 🤦😂

You can try a zapper, but the “partially” means they do react to light, but don’t go towards bright sources. Instead, they seek damp shadow during the day, then start flying during twilight in the general direction of the sky, looking for CO2 traces, and mostly stay put during the night, but occasionally may fly towards warm damp places emitting CO2, which usually means some animal.

The problem with insect repellents, is that they just temporarily move the problem, they don’t fix it. A silent natural repellent would be a citronella plant, if you don’t mind the smell. The fan trick is also technically a repellent, with the benefit that eventually they end up flying in circles until they die of exhaustion. There are “ultrasonic” repellers, but if you have good hearing, they might drive you crazy (they operate at 18-24KHz, I used to hear past 20KHz).

Now that I also have some tinnitus at a perceived frequency above 20KHz, a fan generates enough noise to kind of mask it, and it’s either that or playing some pink noise… so fan it is.

My father used to catch mosquitoes by just waiting until they landed to bite, then slapping them quick. The trick is to pinpoint them by ear, then move your hand to catch them when they jump backwards. That was a useful solution when sharing a camping tent 😅

Another supposed way is to build a “water, sugar, and yeast” trap in a bottle. It’s supposed to emit CO2, attracting the mosquitoes, then trap them in the bottle. Some assembly required. I haven’t had luck with that, though.

My thoughts are… that I’ll see if ChatGPT or something can remove the chaff from that PDF, because oh man, is it full of it.

The problem is “Project 2025”… has already been announced to be renamed “Project 2029” if Trump doesn’t win.

As long as that’s the plan, any Republican win is going to severely erode any remaining US democracy.

“But XY means man!”… unless it doesn’t:

Maybe classes should be based on objective measurements like weight, height, number of limbs, and similar, not on subjective stuff like “doesn’t look girly enough”.

Uhm… what? 🤨

Alternatively: the only people who can invade Russia are the Chinese… and there won’t be a Russia to fix anymore. Hopefully the EU can sign a peace treaty on the EU-China border.

The first China-Spain train already arrived in 2014:

https://en.m.wikipedia.org/wiki/Yiwu–Madrid_railway_line

2024 - World population: 8 Billion.
1974 - World population: 4 Billion.

So, it would take us back to 1974?

People who try to change other’s minds about stuff:

• Politicians
• Activists
• Evangelists
• Marketing Dept

“Influencer” is kind of the generic term.

There is another video from an earlier fight of hers, where she seems to fake an injury to end a combat.

Some other data points:

• She was personally greeted at the Olympics by Georgia Meloni, the current Italy’s fascist populist far-right Prime Minister
• The day before the combat, she tweeted asking whether it is fair for a MAN to fight a WOMAN
• After the 46 second combat, she said to have dropped in the towel because she had “never been hit that hard”, but it “wasn’t for her to decide” whether that was fair
• Then she changed the story to say she realized she wouldn’t win the combat, so she’d rather stop it
• Then claimed she didn’t want to start any of the polemic

The next in the classification, a Hungarian boxer, said that she didn’t care whether the Algerian was a man or a woman, and it was better for her if it was a man because she’s going to feel prouder beating him… and shared this nice meme, which she later deleted:

“I let fentanyl take over me and made a lot of poor decisions”

Uh-um… just to be clear, did fentanyl make him:

• do a stupid prank
• want to melt an sell the metal
• become a racist
• …?

Unpopular opinion: all works of art should be digitized at the highest resolution possible, and shared+replicated as widely as possible… because sooner or later, people are gonna people.

See Middle East, or Italy with its layers upon layers of culture and art, where you can go to many cities and dig straight down through millenia of different cultures.

Things get destroyed, knowledge shouldn’t anymore.

An LLM has… let’s say two core components: a tokenizer, and a neural network. The neural network’s output, is an array of activation levels for a series of neurons, each neuron representing one token. A confidence of 100%, would mean a 100% activation of a single neuron/token, and 0% for all the rest. That is a highly unlikely scenario for a neural network, except when it got overfitted for a single patter during training, and is getting fed the same pattern again. What is more usual, is some value between 0% and 100% for each neuron, with a few neurons showing higher levels of activation, and the LLM… usually picks the highest, but maybe sometimes the second or further one.

The confidence can be calculated by comparing the level of the chosen token’s neuron, to all the other output neurons. A naive one could be level/sum(levels). Somewhat more advanced, could be level²/sum(levels²).

Hallucinations are theoretically possible at a high confidence, but usually happen at lower confidence levels where there are many tokens with a similar confidence.

It seems like it’s hard enough already to get LLMs to distinguish between “killing processes” and murder

It doesn’t look like anything to me… I mean, that could be either part of the guardrails, or a lack of context. A “killing process” is murder, outside the programming/sysadmin context. Current LLMs are still not great at handling different semantic contexts for the same token, and particularly bad at mixing different contexts throughout a single text.

My personal “Turing” test for an LLM, is being able to write a sentence, that could be interpreted in 3 or more ways. For a human, 2 meanings is a somewhat easy task, a double-entendre. Starting at 3 and 4, it becomes a feat. Most LLMs are still at 1, and sometimes struggling.

For example, Gemini says:

Q: Please write a sentence that could be interpreted in two or more ways.

A: I saw her duck into the library.

Q: Please write a sentence that could be interpreted in three or more ways.

A: I’m a text-based AI and can’t assist with that.

It can do paragraphs, though:

Q: Please write a paragraph that could be understood in five or more ways and explain those ways.

A: The old man by the sea watched the horizon, his weathered face a map of untold stories. The sky, a canvas of hues, mirrored the depths of his soul, or perhaps the ocean’s. A gull cried, a mournful symphony or a hopeful call, depending on the listener’s ear. Time, an elusive phantom, danced with eternity in every passing moment, or perhaps stood still, a silent observer of existence.

Interpretations:

Literal: A description of an old man on the beach, observing the sea and sky.
Metaphorical: The old man represents humanity, the sea the subconscious, and the sky the spiritual realm.
Philosophical: A contemplation of time, existence, and the nature of reality.
Psychological: The paragraph delves into the complexities of human perception and interpretation.
Poetic: A piece of evocative prose, inviting multiple readings and interpretations.

…which is pretty neat, but paragraphs have “more degrees of flexibility”, making it way harder to do in a single sentence.